Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation

ArXi:2601.03525v3 Announce Type: replace-cross Effective reward design is a central challenge in Reinforcement Learning (RL) for code generation. Mainstream test-suite-level outcome rewards enforce functional correctness but induce sparsity, while external Reward Models (RMs) provide dense supervision at the cost of misalignment and additional overhead. Since code evaluation naturally yields multiple test-case-level outcomes, partial success, i.e., passing a subset of test cases, offers an intrinsic, verifiable source of dense supervision.